X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/ced7488f6d3a519b2c1b1cbd31048743fb8285bd..59ef81621ff3cb7e9391c44be06483bed7721031:/youtube_dl/extractor/aenetworks.py diff --git a/youtube_dl/extractor/aenetworks.py b/youtube_dl/extractor/aenetworks.py index 6adb6d8..611b948 100644 --- a/youtube_dl/extractor/aenetworks.py +++ b/youtube_dl/extractor/aenetworks.py @@ -1,14 +1,15 @@ +# coding: utf-8 from __future__ import unicode_literals import re from .theplatform import ThePlatformIE from ..utils import ( + extract_attributes, + ExtractorError, + int_or_none, smuggle_url, update_url_query, - unescapeHTML, - extract_attributes, - get_element_by_attribute, ) from ..compat import ( compat_urlparse, @@ -19,23 +20,76 @@ class AENetworksBaseIE(ThePlatformIE): _THEPLATFORM_KEY = 'crazyjava' _THEPLATFORM_SECRET = 's3cr3t' + def _extract_aen_smil(self, smil_url, video_id, auth=None): + query = {'mbr': 'true'} + if auth: + query['auth'] = auth + TP_SMIL_QUERY = [{ + 'assetTypes': 'high_video_ak', + 'switch': 'hls_high_ak' + }, { + 'assetTypes': 'high_video_s3' + }, { + 'assetTypes': 'high_video_s3', + 'switch': 'hls_ingest_fastly' + }] + formats = [] + subtitles = {} + last_e = None + for q in TP_SMIL_QUERY: + q.update(query) + m_url = update_url_query(smil_url, q) + m_url = self._sign_url(m_url, self._THEPLATFORM_KEY, self._THEPLATFORM_SECRET) + try: + tp_formats, tp_subtitles = self._extract_theplatform_smil( + m_url, video_id, 'Downloading %s SMIL data' % (q.get('switch') or q['assetTypes'])) + except ExtractorError as e: + last_e = e + continue + formats.extend(tp_formats) + subtitles = self._merge_subtitles(subtitles, tp_subtitles) + if last_e and not formats: + raise last_e + self._sort_formats(formats) + return { + 'id': video_id, + 'formats': formats, + 'subtitles': subtitles, + } + class AENetworksIE(AENetworksBaseIE): IE_NAME = 'aenetworks' - IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network' - _VALID_URL = r'https?://(?:www\.)?(?P(?:history|aetv|mylifetime)\.com|fyi\.tv)/(?:shows/(?P[^/]+(?:/[^/]+){0,2})|movies/(?P[^/]+)/full-movie)' + IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network and History Vault' + _VALID_URL = r'''(?x) + https?:// + (?:www\.)? + (?P + (?:history(?:vault)?|aetv|mylifetime|lifetimemovieclub)\.com| + fyi\.tv + )/ + (?: + shows/(?P[^/]+(?:/[^/]+){0,2})| + movies/(?P[^/]+)(?:/full-movie)?| + specials/(?P[^/]+)/(?:full-special|preview-)| + collections/[^/]+/(?P[^/]+) + ) + ''' _TESTS = [{ 'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1', - 'md5': '8ff93eb073449f151d6b90c0ae1ef0c7', 'info_dict': { 'id': '22253814', 'ext': 'mp4', - 'title': 'Winter Is Coming', + 'title': 'Winter is Coming', 'description': 'md5:641f424b7a19d8e24f26dea22cf59d74', 'timestamp': 1338306241, 'upload_date': '20120529', 'uploader': 'AENE-NEW', }, + 'params': { + # m3u8 download + 'skip_download': True, + }, 'add_ie': ['ThePlatform'], }, { 'url': 'http://www.history.com/shows/ancient-aliens/season-1', @@ -62,18 +116,31 @@ class AENetworksIE(AENetworksBaseIE): }, { 'url': 'http://www.mylifetime.com/movies/center-stage-on-pointe/full-movie', 'only_matching': True + }, { + 'url': 'https://www.lifetimemovieclub.com/movies/a-killer-among-us', + 'only_matching': True + }, { + 'url': 'http://www.history.com/specials/sniper-into-the-kill-zone/full-special', + 'only_matching': True + }, { + 'url': 'https://www.historyvault.com/collections/america-the-story-of-us/westward', + 'only_matching': True + }, { + 'url': 'https://www.aetv.com/specials/hunting-jonbenets-killer-the-untold-story/preview-hunting-jonbenets-killer-the-untold-story', + 'only_matching': True }] _DOMAIN_TO_REQUESTOR_ID = { 'history.com': 'HISTORY', 'aetv.com': 'AETV', 'mylifetime.com': 'LIFETIME', + 'lifetimemovieclub.com': 'LIFETIMEMOVIECLUB', 'fyi.tv': 'FYI', } def _real_extract(self, url): - domain, show_path, movie_display_id = re.match(self._VALID_URL, url).groups() - display_id = show_path or movie_display_id - webpage = self._download_webpage(url, display_id) + domain, show_path, movie_display_id, special_display_id, collection_display_id = re.match(self._VALID_URL, url).groups() + display_id = show_path or movie_display_id or special_display_id or collection_display_id + webpage = self._download_webpage(url, display_id, headers=self.geo_verification_headers()) if show_path: url_parts = show_path.split('/') url_parts_len = len(url_parts) @@ -82,89 +149,67 @@ class AENetworksIE(AENetworksBaseIE): for season_url_path in re.findall(r'(?s)]+data-href="(/shows/%s/season-\d+)"' % url_parts[0], webpage): entries.append(self.url_result( compat_urlparse.urljoin(url, season_url_path), 'AENetworks')) - return self.playlist_result( - entries, self._html_search_meta('aetn:SeriesId', webpage), - self._html_search_meta('aetn:SeriesTitle', webpage)) - elif url_parts_len == 2: + if entries: + return self.playlist_result( + entries, self._html_search_meta('aetn:SeriesId', webpage), + self._html_search_meta('aetn:SeriesTitle', webpage)) + else: + # single season + url_parts_len = 2 + if url_parts_len == 2: entries = [] - for episode_item in re.findall(r'(?s)]+class="[^"]*episode-item[^"]*"[^>]*>', webpage): + for episode_item in re.findall(r'(?s)<[^>]+class="[^"]*(?:episode|program)-item[^"]*"[^>]*>', webpage): episode_attributes = extract_attributes(episode_item) episode_url = compat_urlparse.urljoin( url, episode_attributes['data-canonical']) entries.append(self.url_result( episode_url, 'AENetworks', - episode_attributes['data-videoid'])) + episode_attributes.get('data-videoid') or episode_attributes.get('data-video-id'))) return self.playlist_result( entries, self._html_search_meta('aetn:SeasonId', webpage)) - query = { - 'mbr': 'true', - 'assetTypes': 'medium_video_s3' - } video_id = self._html_search_meta('aetn:VideoID', webpage) media_url = self._search_regex( - r"media_url\s*=\s*'([^']+)'", webpage, 'video url') + [r"media_url\s*=\s*'(?P[^']+)'", + r'data-media-url=(?P(?:https?:)?//[^\s>]+)', + r'data-media-url=(["\'])(?P(?:(?!\1).)+?)\1'], + webpage, 'video url', group='url') theplatform_metadata = self._download_theplatform_metadata(self._search_regex( - r'https?://link.theplatform.com/s/([^?]+)', media_url, 'theplatform_path'), video_id) + r'https?://link\.theplatform\.com/s/([^?]+)', media_url, 'theplatform_path'), video_id) info = self._parse_theplatform_metadata(theplatform_metadata) + auth = None if theplatform_metadata.get('AETN$isBehindWall'): requestor_id = self._DOMAIN_TO_REQUESTOR_ID[domain] resource = self._get_mvpd_resource( requestor_id, theplatform_metadata['title'], theplatform_metadata.get('AETN$PPL_pplProgramId') or theplatform_metadata.get('AETN$PPL_pplProgramId_OLD'), theplatform_metadata['ratings'][0]['rating']) - query['auth'] = self._extract_mvpd_auth( + auth = self._extract_mvpd_auth( url, video_id, requestor_id, resource) info.update(self._search_json_ld(webpage, video_id, fatal=False)) - media_url = update_url_query(media_url, query) - media_url = self._sign_url(media_url, self._THEPLATFORM_KEY, self._THEPLATFORM_SECRET) - formats, subtitles = self._extract_theplatform_smil(media_url, video_id) - self._sort_formats(formats) - info.update({ - 'id': video_id, - 'formats': formats, - 'subtitles': subtitles, - }) + info.update(self._extract_aen_smil(media_url, video_id, auth)) return info class HistoryTopicIE(AENetworksBaseIE): IE_NAME = 'history:topic' IE_DESC = 'History.com Topic' - _VALID_URL = r'https?://(?:www\.)?history\.com/topics/(?:[^/]+/)?(?P[^/]+)(?:/[^/]+(?:/(?P[^/?#]+))?)?' + _VALID_URL = r'https?://(?:www\.)?history\.com/topics/[^/]+/(?P[\w+-]+?)-video' _TESTS = [{ - 'url': 'http://www.history.com/topics/valentines-day/history-of-valentines-day/videos/bet-you-didnt-know-valentines-day?m=528e394da93ae&s=undefined&f=1&free=false', + 'url': 'https://www.history.com/topics/valentines-day/history-of-valentines-day-video', 'info_dict': { 'id': '40700995724', 'ext': 'mp4', - 'title': "Bet You Didn't Know: Valentine's Day", + 'title': "History of Valentine’s Day", 'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7', 'timestamp': 1375819729, 'upload_date': '20130806', - 'uploader': 'AENE-NEW', }, 'params': { # m3u8 download 'skip_download': True, }, 'add_ie': ['ThePlatform'], - }, { - 'url': 'http://www.history.com/topics/world-war-i/world-war-i-history/videos', - 'info_dict': - { - 'id': 'world-war-i-history', - 'title': 'World War I History', - }, - 'playlist_mincount': 24, - }, { - 'url': 'http://www.history.com/topics/world-war-i-history/videos', - 'only_matching': True, - }, { - 'url': 'http://www.history.com/topics/world-war-i/world-war-i-history', - 'only_matching': True, - }, { - 'url': 'http://www.history.com/topics/world-war-i/world-war-i-history/speeches', - 'only_matching': True, }] def theplatform_url_result(self, theplatform_url, video_id, query): @@ -184,25 +229,19 @@ class HistoryTopicIE(AENetworksBaseIE): } def _real_extract(self, url): - topic_id, video_display_id = re.match(self._VALID_URL, url).groups() - if video_display_id: - webpage = self._download_webpage(url, video_display_id) - release_url, video_id = re.search(r"_videoPlayer.play\('([^']+)'\s*,\s*'[^']+'\s*,\s*'(\d+)'\)", webpage).groups() - release_url = unescapeHTML(release_url) - - return self.theplatform_url_result( - release_url, video_id, { - 'mbr': 'true', - 'switch': 'hls' - }) - else: - webpage = self._download_webpage(url, topic_id) - entries = [] - for episode_item in re.findall(r']*>', webpage): - video_attributes = extract_attributes(episode_item) - entries.append(self.theplatform_url_result( - video_attributes['data-release-url'], video_attributes['data-id'], { - 'mbr': 'true', - 'switch': 'hls' - })) - return self.playlist_result(entries, topic_id, get_element_by_attribute('class', 'show-title', webpage)) + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + video_id = self._search_regex( + r']+src="[^"]+\btpid=(\d+)', webpage, 'tpid') + result = self._download_json( + 'https://feeds.video.aetnd.com/api/v2/history/videos', + video_id, query={'filter[id]': video_id})['results'][0] + title = result['title'] + info = self._extract_aen_smil(result['publicUrl'], video_id) + info.update({ + 'title': title, + 'description': result.get('description'), + 'duration': int_or_none(result.get('duration')), + 'timestamp': int_or_none(result.get('added'), 1000), + }) + return info